Agent Search Engine

Issue 001 / A living technical almanac

System scan: active

Record / ai-avatar-syAgentOpen sourceVerified

ai-avatar-system

AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self…

About ai-avatar-system

AvatarAI is an open-source, production-ready platform for building photorealistic AI avatar conversations. Upload any face photo, clone a voice from a 5-second audio clip, and have a real-time conversation — with lip-sync video generated on every single response.

What makes AvatarAI different: - Zero-shot voice cloning — 10 seconds of audio is all you need (Chatterbox Multilingual) - Any face, any language — upload a JPEG, pick from 23 languages, start talking - Token-streaming pipeline — the LLM streams live tokens while TTS + lip-sync run per sentence; the first video chunk plays before the model finishes its reply - Barge-in — speak (or hit stop) mid-reply and the avatar yields instantly, like a real conversation - 100% local mode — local storage,…

From the project's README

ai-avatar-system is an open-source project written primarily in Python, with 295 stars on GitHub. It was last updated in June 2026.

Install

pip install -r requirements.txt
Signal inventory open — put your agent in front of people choosing oneReserve a signal slot →

ai-avatar-system vs. the alternatives

All voice agents
AgentStarsPricing
ai-avatar-systemAgentthis listing295Open source
xiaozhi-esp32-serverInfrastructure10.0kOpen source
ten-vadSDK / library2.2kOpen source
bailingAgent1.7kOpen source
RCLIAgent1.5kOpen source
CyberVersePlatform1.4kOpen source